© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 2868
    Prev
    Next
    INDEX
    Explanations

    nigga/nigger

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ות
    0.45
    idamente
    0.43
    𝑒
    0.43
    تها
    0.39
    𝗧
    0.39
    t
    0.39
    𝗞
    0.39
    𝑡
    0.38
     já
    0.38
    ง
    0.38
    POSITIVE LOGITS
    ный
    0.46
     mực
    0.41
    backslash
    0.40
    lmfit
    0.39
    wedge
    0.39
    ку
    0.38
    stown
    0.37
    χος
    0.36
    Ал
    0.36
    regierung
    0.36
    Activations Density 0.008%

    No Known Activations